aiplatform/api/AIPlatform.Samples/MultimodalVideoInput.cs (43 lines of code) (raw):

/* * Copyright 2024 Google LLC * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * https://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ // [START generativeaionvertexai_gemini_single_turn_video] using Google.Api.Gax.Grpc; using Google.Cloud.AIPlatform.V1; using System.Text; using System.Threading.Tasks; public class MultimodalVideoInput { public async Task<string> GenerateContent( string projectId = "your-project-id", string location = "us-central1", string publisher = "google", string model = "gemini-2.0-flash-001" ) { var predictionServiceClient = new PredictionServiceClientBuilder { Endpoint = $"{location}-aiplatform.googleapis.com" }.Build(); var generateContentRequest = new GenerateContentRequest { Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}", Contents = { new Content { Role = "USER", Parts = { new Part { Text = "What's in the video?" }, new Part { FileData = new() { MimeType = "video/mp4", FileUri = "gs://cloud-samples-data/video/animals.mp4" }} } } } }; using PredictionServiceClient.StreamGenerateContentStream response = predictionServiceClient.StreamGenerateContent(generateContentRequest); StringBuilder fullText = new(); AsyncResponseStream<GenerateContentResponse> responseStream = response.GetResponseStream(); await foreach (GenerateContentResponse responseItem in responseStream) { fullText.Append(responseItem.Candidates[0].Content.Parts[0].Text); } return fullText.ToString(); } } // [END generativeaionvertexai_gemini_single_turn_video]